[PATCH] D120544: [AMDGPU] Omit unnecessary waitcnt before barriers

Fri Feb 25 01:29:05 PST 2022

foad added a comment.

In D120544#3344977 <https://reviews.llvm.org/D120544#3344977>, @kerbowa wrote:

> The test waitcnt-vscnt.ll is kind of muddied by this patch. It was relying on the behavior of s_barrier always adding s_waitcnt_vscnt at barriers if there were any outstanding events. The singlethread fences were not actually doing anything. I've added workgroup fences instead. With workgroup fences we currently always add the waitcnt. The test will look as it did before after my memory legalizer/waitcnt overhaul so that these are optimized. Consider this a precommit of this test for now.

Can you split this into two patches: first change the test, and then rebase this patch?

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D120544/new/

https://reviews.llvm.org/D120544